Imporing Required Libraries

import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sb

creditcard_df = pd.read_csv('Marketing_data.csv')

creditcard_df.head()

	CUST_ID	BALANCE	BALANCE_FREQUENCY	PURCHASES	ONEOFF_PURCHASES	INSTALLMENTS_PURCHASES	CASH_ADVANCE	PURCHASES_FREQUENCY	ONEOFF_PURCHASES_FREQUENCY	PURCHASES_INSTALLMENTS_FREQUENCY	CASH_ADVANCE_FREQUENCY	CASH_ADVANCE_TRX	PURCHASES_TRX	CREDIT_LIMIT	PAYMENTS	MINIMUM_PAYMENTS	PRC_FULL_PAYMENT	TENURE
0	C10001	40.900749	0.818182	95.40	0.00	95.4	0.000000	0.166667	0.000000	0.083333	0.000000	0	2	1000.0	201.802084	139.509787	0.000000	12
1	C10002	3202.467416	0.909091	0.00	0.00	0.0	6442.945483	0.000000	0.000000	0.000000	0.250000	4	0	7000.0	4103.032597	1072.340217	0.222222	12
2	C10003	2495.148862	1.000000	773.17	773.17	0.0	0.000000	1.000000	1.000000	0.000000	0.000000	0	12	7500.0	622.066742	627.284787	0.000000	12
3	C10004	1666.670542	0.636364	1499.00	1499.00	0.0	205.788017	0.083333	0.083333	0.000000	0.083333	1	1	7500.0	0.000000	NaN	0.000000	12
4	C10005	817.714335	1.000000	16.00	16.00	0.0	0.000000	0.083333	0.083333	0.000000	0.000000	0	1	1200.0	678.334763	244.791237	0.000000	12

creditcard_df.shape

(8950, 18)

creditcard_df.columns

Index(['CUST_ID', 'BALANCE', 'BALANCE_FREQUENCY', 'PURCHASES',
       'ONEOFF_PURCHASES', 'INSTALLMENTS_PURCHASES', 'CASH_ADVANCE',
       'PURCHASES_FREQUENCY', 'ONEOFF_PURCHASES_FREQUENCY',
       'PURCHASES_INSTALLMENTS_FREQUENCY', 'CASH_ADVANCE_FREQUENCY',
       'CASH_ADVANCE_TRX', 'PURCHASES_TRX', 'CREDIT_LIMIT', 'PAYMENTS',
       'MINIMUM_PAYMENTS', 'PRC_FULL_PAYMENT', 'TENURE'],
      dtype='object')

creditcard_df.dtypes

CUST_ID                              object
BALANCE                             float64
BALANCE_FREQUENCY                   float64
PURCHASES                           float64
ONEOFF_PURCHASES                    float64
INSTALLMENTS_PURCHASES              float64
CASH_ADVANCE                        float64
PURCHASES_FREQUENCY                 float64
ONEOFF_PURCHASES_FREQUENCY          float64
PURCHASES_INSTALLMENTS_FREQUENCY    float64
CASH_ADVANCE_FREQUENCY              float64
CASH_ADVANCE_TRX                      int64
PURCHASES_TRX                         int64
CREDIT_LIMIT                        float64
PAYMENTS                            float64
MINIMUM_PAYMENTS                    float64
PRC_FULL_PAYMENT                    float64
TENURE                                int64
dtype: object

creditcard_df.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 8950 entries, 0 to 8949
Data columns (total 18 columns):
 #   Column                            Non-Null Count  Dtype  
---  ------                            --------------  -----  
 0   CUST_ID                           8950 non-null   object 
 1   BALANCE                           8950 non-null   float64
 2   BALANCE_FREQUENCY                 8950 non-null   float64
 3   PURCHASES                         8950 non-null   float64
 4   ONEOFF_PURCHASES                  8950 non-null   float64
 5   INSTALLMENTS_PURCHASES            8950 non-null   float64
 6   CASH_ADVANCE                      8950 non-null   float64
 7   PURCHASES_FREQUENCY               8950 non-null   float64
 8   ONEOFF_PURCHASES_FREQUENCY        8950 non-null   float64
 9   PURCHASES_INSTALLMENTS_FREQUENCY  8950 non-null   float64
 10  CASH_ADVANCE_FREQUENCY            8950 non-null   float64
 11  CASH_ADVANCE_TRX                  8950 non-null   int64  
 12  PURCHASES_TRX                     8950 non-null   int64  
 13  CREDIT_LIMIT                      8949 non-null   float64
 14  PAYMENTS                          8950 non-null   float64
 15  MINIMUM_PAYMENTS                  8637 non-null   float64
 16  PRC_FULL_PAYMENT                  8950 non-null   float64
 17  TENURE                            8950 non-null   int64  
dtypes: float64(14), int64(3), object(1)
memory usage: 1.2+ MB

creditcard_df.describe()

	BALANCE	BALANCE_FREQUENCY	PURCHASES	ONEOFF_PURCHASES	INSTALLMENTS_PURCHASES	CASH_ADVANCE	PURCHASES_FREQUENCY	ONEOFF_PURCHASES_FREQUENCY	PURCHASES_INSTALLMENTS_FREQUENCY	CASH_ADVANCE_FREQUENCY	CASH_ADVANCE_TRX	PURCHASES_TRX	CREDIT_LIMIT	PAYMENTS	MINIMUM_PAYMENTS	PRC_FULL_PAYMENT	TENURE
count	8950.000000	8950.000000	8950.000000	8950.000000	8950.000000	8950.000000	8950.000000	8950.000000	8950.000000	8950.000000	8950.000000	8950.000000	8949.000000	8950.000000	8637.000000	8950.000000	8950.000000
mean	1564.474828	0.877271	1003.204834	592.437371	411.067645	978.871112	0.490351	0.202458	0.364437	0.135144	3.248827	14.709832	4494.449450	1733.143852	864.206542	0.153715	11.517318
std	2081.531879	0.236904	2136.634782	1659.887917	904.338115	2097.163877	0.401371	0.298336	0.397448	0.200121	6.824647	24.857649	3638.815725	2895.063757	2372.446607	0.292499	1.338331
min	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	50.000000	0.000000	0.019163	0.000000	6.000000
25%	128.281915	0.888889	39.635000	0.000000	0.000000	0.000000	0.083333	0.000000	0.000000	0.000000	0.000000	1.000000	1600.000000	383.276166	169.123707	0.000000	12.000000
50%	873.385231	1.000000	361.280000	38.000000	89.000000	0.000000	0.500000	0.083333	0.166667	0.000000	0.000000	7.000000	3000.000000	856.901546	312.343947	0.000000	12.000000
75%	2054.140036	1.000000	1110.130000	577.405000	468.637500	1113.821139	0.916667	0.300000	0.750000	0.222222	4.000000	17.000000	6500.000000	1901.134317	825.485459	0.142857	12.000000
max	19043.138560	1.000000	49039.570000	40761.250000	22500.000000	47137.211760	1.000000	1.000000	1.000000	1.500000	123.000000	358.000000	30000.000000	50721.483360	76406.207520	1.000000	12.000000

Value Counts

for col in list(creditcard_df):
    print(col)
    print(creditcard_df[col].unique())

CUST_ID
['C10001' 'C10002' 'C10003' ... 'C19188' 'C19189' 'C19190']
BALANCE
[  40.900749 3202.467416 2495.148862 ...   23.398673   13.457564
  372.708075]
BALANCE_FREQUENCY
[0.818182 0.909091 1.       0.636364 0.545455 0.875    0.454545 0.727273
 0.5      0.888889 0.090909 0.272727 0.363636 0.       0.666667 0.75
 0.857143 0.181818 0.333333 0.6      0.3      0.125    0.9      0.833333
 0.8      0.2      0.777778 0.555556 0.25     0.142857 0.571429 0.4
 0.444444 0.714286 0.222222 0.1      0.625    0.428571 0.111111 0.285714
 0.7      0.375    0.166667]
PURCHASES
[  95.4     0.    773.17 ...  291.12  144.4  1093.25]
ONEOFF_PURCHASES
[   0.    773.17 1499.   ...  734.4  1012.73 1093.25]
INSTALLMENTS_PURCHASES
[  95.4     0.   1333.28 ...  113.28  291.12  144.4 ]
CASH_ADVANCE
[   0.       6442.945483  205.788017 ... 8555.409326   36.558778
  127.040008]
PURCHASES_FREQUENCY
[0.166667 0.       1.       0.083333 0.666667 0.333333 0.25     0.75
 0.5      0.416667 0.916667 0.583333 0.375    0.625    0.272727 0.833333
 0.909091 0.111111 0.142857 0.090909 0.363636 0.1      0.875    0.125
 0.818182 0.636364 0.2      0.8      0.3      0.9      0.285714 0.727273
 0.181818 0.7      0.545455 0.888889 0.714286 0.454545 0.857143 0.555556
 0.428571 0.4      0.571429 0.6      0.222222 0.777778 0.444444]
ONEOFF_PURCHASES_FREQUENCY
[0.       1.       0.083333 0.166667 0.25     0.916667 0.5      0.416667
 0.333333 0.666667 0.375    0.583333 0.1      0.090909 0.833333 0.75
 0.111111 0.142857 0.125    0.875    0.363636 0.2      0.818182 0.8
 0.3      0.636364 0.181818 0.909091 0.285714 0.222222 0.727273 0.571429
 0.6      0.272727 0.714286 0.545455 0.428571 0.444444 0.454545 0.625
 0.777778 0.555556 0.7      0.9      0.4      0.857143 0.888889]
PURCHASES_INSTALLMENTS_FREQUENCY
[0.083333 0.       0.583333 1.       0.25     0.916667 0.75     0.5
 0.333333 0.666667 0.416667 0.166667 0.833333 0.4      0.181818 0.818182
 0.272727 0.375    0.125    0.636364 0.545455 0.909091 0.888889 0.2
 0.8      0.1      0.142857 0.857143 0.444444 0.454545 0.111111 0.6
 0.555556 0.777778 0.3      0.9      0.363636 0.714286 0.875    0.222222
 0.285714 0.7      0.727273 0.571429 0.090909 0.428571 0.625   ]
CASH_ADVANCE_FREQUENCY
[0.       0.25     0.083333 0.166667 0.333333 0.363636 0.833333 0.5
 0.727273 0.125    0.875    0.111111 0.416667 0.181818 0.545455 0.75
 0.142857 0.583333 0.666667 0.222222 0.285714 0.909091 0.2      0.625
 0.090909 0.4      1.       0.8      0.636364 0.3      0.916667 0.444444
 1.25     0.1      0.428571 0.272727 0.555556 0.6      0.454545 1.166667
 0.375    0.777778 0.714286 0.571429 0.857143 1.125    1.1      1.5
 0.7      0.818182 0.9      0.888889 1.090909 1.142857]
CASH_ADVANCE_TRX
[  0   4   1   3   6  13   5  16  10   2  11   7  12  37  27  23  21  14
  40   8   9  26  15  18  28  24  20  17  22  31 123  52  51  62  19  25
  30  29  53  45  43  42 107  38  56  39  32  33  50  34  63  36 110  47
  48  71  35  93  80  44  61  46  49  69  41]
PURCHASES_TRX
[  2   0  12   1   8  64   5   3   6  26  11   9  92  17  13  45  14  41
  27  20  87  18   4  42  61  33   7  50  22  23  60  46  75  31  10  34
  81  25  85 217  19  52 216  97  24  77 130  90  44  39  15  30  36 123
 151  21 101  49  98  28  84  93  72  38  99  62  48  16  32  51  74  29
  59  76  47 126 229  40 103 121 157 114  53  83  43  54 222  66 141  37
  79  70  80 194 117 100 111  67 219  55 152 104 182  88  82  71  78  35
 122 105 108  69 175 135  91  65  68 119  63 140 113 358  58 248 129  56
  89  57 139 176 136 195  73 109 208 115 110 147 273 102 185 171 168 232
  95  86 148 112 128 254 198 298 154 116 142 131 347 204 200  94 118 344
 162 308 199 309  96 274 224 143 133 127 186]
CREDIT_LIMIT
[ 1000.        7000.        7500.        1200.        1800.
 13500.        2300.       11000.        2000.        3000.
  8000.        2500.       13000.        4000.       11250.
  9000.        6000.        1700.       10500.        6900.
  5000.        4500.        1500.        8500.        2400.
  4200.        3300.       12000.        3500.        6500.
  1600.        4150.        1850.        6250.        2250.
  9500.       16500.        5700.        5500.       17000.
  3200.       19000.        2800.       18000.       21500.
 10000.       20000.        7900.       15000.       12500.
 14000.        5300.         900.        6150.       11500.
 23000.        2700.       14500.       19500.        1400.
  2900.        1950.        7200.       10950.        2100.
   500.       21000.        4800.        7300.       18500.
  6550.        6200.        3150.       11800.       11300.
  2750.       10300.        2850.       17500.       22500.
  6750.       16000.        1750.       15500.        3800.
  6600.        3650.        2600.        4600.        3350.
  4300.        5250.       28000.        3600.       10200.
   750.        7600.        2720.        2200.        7350.
   300.        3750.        1900.       10400.        5200.
  4350.        3050.        6700.       20500.        5750.
  8300.        7950.        3100.        4050.        6300.
  3666.666667   200.        9100.        3700.        7100.
  4750.        3900.       10100.        1300.       19600.
 10450.       11150.         600.        4700.         150.
  3400.        1350.        5100.        7227.272727 13550.
  9200.        6100.        2050.        6400.        4250.
 14600.        8600.        3511.111111  5600.        6727.272727
 13600.        8800.       11100.       12200.        8100.
  8050.        4100.        5550.        4450.        5650.
  8200.        5400.       25000.        9950.        1150.
  6800.        4650.        7800.        2150.       22000.
   400.        7700.        4400.        1050.         700.
  5181.818182  4900.        1100.        2550.        2283.333333
 30000.        9700.        9400.                nan  2725.
   450.        8700.       12300.        7050.        1550.
  9800.        5450.         800.        8954.545455  2950.
  2450.        6850.        4950.        5900.        1250.
 17150.        9600.          50.       10750.        1120.
 13450.        3777.777778   650.        1450.        2350.
  1833.333333]
PAYMENTS
[ 201.802084 4103.032597  622.066742 ...   81.270775   52.549959
   63.165404]
MINIMUM_PAYMENTS
[ 139.509787 1072.340217  627.284787 ...   82.418369   55.755628
   88.288956]
PRC_FULL_PAYMENT
[0.       0.222222 1.       0.25     0.083333 0.3      0.333333 0.166667
 0.111111 0.916667 0.2      0.090909 0.454545 0.181818 0.444444 0.636364
 0.5      0.75     0.142857 0.888889 0.545455 0.818182 0.363636 0.833333
 0.666667 0.909091 0.1      0.583333 0.8      0.416667 0.4      0.125
 0.714286 0.6      0.571429 0.375    0.9      0.285714 0.7      0.272727
 0.777778 0.875    0.727273 0.428571 0.625    0.857143 0.555556]
TENURE
[12  8 11  9 10  7  6]

for col in list(creditcard_df):
    print(col, creditcard_df[col].nunique(), sep='--->')

CUST_ID--->8950

BALANCE--->8871

BALANCE_FREQUENCY--->43

PURCHASES--->6203

ONEOFF_PURCHASES--->4014

INSTALLMENTS_PURCHASES--->4452

CASH_ADVANCE--->4323

PURCHASES_FREQUENCY--->47

ONEOFF_PURCHASES_FREQUENCY--->47

PURCHASES_INSTALLMENTS_FREQUENCY--->47

CASH_ADVANCE_FREQUENCY--->54

CASH_ADVANCE_TRX--->65

PURCHASES_TRX--->173

CREDIT_LIMIT--->205

PAYMENTS--->8711

MINIMUM_PAYMENTS--->8636

PRC_FULL_PAYMENT--->47

TENURE--->7

creditcard_df.describe()

	BALANCE	BALANCE_FREQUENCY	PURCHASES	ONEOFF_PURCHASES	INSTALLMENTS_PURCHASES	CASH_ADVANCE	PURCHASES_FREQUENCY	ONEOFF_PURCHASES_FREQUENCY	PURCHASES_INSTALLMENTS_FREQUENCY	CASH_ADVANCE_FREQUENCY	CASH_ADVANCE_TRX	PURCHASES_TRX	CREDIT_LIMIT	PAYMENTS	MINIMUM_PAYMENTS	PRC_FULL_PAYMENT	TENURE
count	8950.000000	8950.000000	8950.000000	8950.000000	8950.000000	8950.000000	8950.000000	8950.000000	8950.000000	8950.000000	8950.000000	8950.000000	8949.000000	8950.000000	8637.000000	8950.000000	8950.000000
mean	1564.474828	0.877271	1003.204834	592.437371	411.067645	978.871112	0.490351	0.202458	0.364437	0.135144	3.248827	14.709832	4494.449450	1733.143852	864.206542	0.153715	11.517318
std	2081.531879	0.236904	2136.634782	1659.887917	904.338115	2097.163877	0.401371	0.298336	0.397448	0.200121	6.824647	24.857649	3638.815725	2895.063757	2372.446607	0.292499	1.338331
min	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	50.000000	0.000000	0.019163	0.000000	6.000000
25%	128.281915	0.888889	39.635000	0.000000	0.000000	0.000000	0.083333	0.000000	0.000000	0.000000	0.000000	1.000000	1600.000000	383.276166	169.123707	0.000000	12.000000
50%	873.385231	1.000000	361.280000	38.000000	89.000000	0.000000	0.500000	0.083333	0.166667	0.000000	0.000000	7.000000	3000.000000	856.901546	312.343947	0.000000	12.000000
75%	2054.140036	1.000000	1110.130000	577.405000	468.637500	1113.821139	0.916667	0.300000	0.750000	0.222222	4.000000	17.000000	6500.000000	1901.134317	825.485459	0.142857	12.000000
max	19043.138560	1.000000	49039.570000	40761.250000	22500.000000	47137.211760	1.000000	1.000000	1.000000	1.500000	123.000000	358.000000	30000.000000	50721.483360	76406.207520	1.000000	12.000000

Filtering Data

creditcard_df[creditcard_df['PURCHASES'] == 49039.570000]

	CUST_ID	BALANCE	BALANCE_FREQUENCY	PURCHASES	ONEOFF_PURCHASES	INSTALLMENTS_PURCHASES	CASH_ADVANCE	PURCHASES_FREQUENCY	ONEOFF_PURCHASES_FREQUENCY	PURCHASES_INSTALLMENTS_FREQUENCY	CASH_ADVANCE_FREQUENCY	CASH_ADVANCE_TRX	PURCHASES_TRX	CREDIT_LIMIT	PAYMENTS	MINIMUM_PAYMENTS	PRC_FULL_PAYMENT	TENURE
550	C10574	11547.52001	1.0	49039.57	40761.25	8278.32	558.166886	1.0	1.0	0.916667	0.083333	1	101	22500.0	46930.59824	2974.069421	0.25	12

creditcard_df[creditcard_df['CASH_ADVANCE'] == 0.000000]

	CUST_ID	BALANCE	BALANCE_FREQUENCY	PURCHASES	ONEOFF_PURCHASES	INSTALLMENTS_PURCHASES	CASH_ADVANCE	PURCHASES_FREQUENCY	ONEOFF_PURCHASES_FREQUENCY	PURCHASES_INSTALLMENTS_FREQUENCY	CASH_ADVANCE_FREQUENCY	CASH_ADVANCE_TRX	PURCHASES_TRX	CREDIT_LIMIT	PAYMENTS	MINIMUM_PAYMENTS	PRC_FULL_PAYMENT	TENURE
0	C10001	40.900749	0.818182	95.40	0.00	95.40	0.0	0.166667	0.000000	0.083333	0.0	0	2	1000.0	201.802084	139.509787	0.00	12
2	C10003	2495.148862	1.000000	773.17	773.17	0.00	0.0	1.000000	1.000000	0.000000	0.0	0	12	7500.0	622.066742	627.284787	0.00	12
4	C10005	817.714335	1.000000	16.00	16.00	0.00	0.0	0.083333	0.083333	0.000000	0.0	0	1	1200.0	678.334763	244.791237	0.00	12
5	C10006	1809.828751	1.000000	1333.28	0.00	1333.28	0.0	0.666667	0.000000	0.583333	0.0	0	8	1800.0	1400.057770	2407.246035	0.00	12
6	C10007	627.260806	1.000000	7091.01	6402.63	688.38	0.0	1.000000	1.000000	1.000000	0.0	0	64	13500.0	6354.314328	198.065894	1.00	12
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
8943	C19184	5.871712	0.500000	20.90	20.90	0.00	0.0	0.166667	0.166667	0.000000	0.0	0	1	500.0	58.644883	43.473717	0.00	6
8944	C19185	193.571722	0.833333	1012.73	1012.73	0.00	0.0	0.333333	0.333333	0.000000	0.0	0	2	4000.0	0.000000	NaN	0.00	6
8945	C19186	28.493517	1.000000	291.12	0.00	291.12	0.0	1.000000	0.000000	0.833333	0.0	0	6	1000.0	325.594462	48.886365	0.50	6
8946	C19187	19.183215	1.000000	300.00	0.00	300.00	0.0	1.000000	0.000000	0.833333	0.0	0	6	1000.0	275.861322	NaN	0.00	6
8947	C19188	23.398673	0.833333	144.40	0.00	144.40	0.0	0.833333	0.000000	0.666667	0.0	0	5	1000.0	81.270775	82.418369	0.25	6

4628 rows × 18 columns

Missing Values Treatment

creditcard_df.isnull().sum()

CUST_ID                               0
BALANCE                               0
BALANCE_FREQUENCY                     0
PURCHASES                             0
ONEOFF_PURCHASES                      0
INSTALLMENTS_PURCHASES                0
CASH_ADVANCE                          0
PURCHASES_FREQUENCY                   0
ONEOFF_PURCHASES_FREQUENCY            0
PURCHASES_INSTALLMENTS_FREQUENCY      0
CASH_ADVANCE_FREQUENCY                0
CASH_ADVANCE_TRX                      0
PURCHASES_TRX                         0
CREDIT_LIMIT                          1
PAYMENTS                              0
MINIMUM_PAYMENTS                    313
PRC_FULL_PAYMENT                      0
TENURE                                0
dtype: int64

sb.heatmap(creditcard_df.isnull(), cmap='Oranges_r', yticklabels=False)

<AxesSubplot:>

mean_value = creditcard_df['MINIMUM_PAYMENTS'].mean()
mean_value

864.2065423050816

creditcard_df['MINIMUM_PAYMENTS'].fillna(value=mean_value, inplace=True)

mean_value = creditcard_df['CREDIT_LIMIT'].mean()
mean_value

4494.043836631879

creditcard_df['CREDIT_LIMIT'].fillna(value=mean_value, inplace=True)

creditcard_df.isnull().sum()

CUST_ID                             0
BALANCE                             0
BALANCE_FREQUENCY                   0
PURCHASES                           0
ONEOFF_PURCHASES                    0
INSTALLMENTS_PURCHASES              0
CASH_ADVANCE                        0
PURCHASES_FREQUENCY                 0
ONEOFF_PURCHASES_FREQUENCY          0
PURCHASES_INSTALLMENTS_FREQUENCY    0
CASH_ADVANCE_FREQUENCY              0
CASH_ADVANCE_TRX                    0
PURCHASES_TRX                       0
CREDIT_LIMIT                        0
PAYMENTS                            0
MINIMUM_PAYMENTS                    0
PRC_FULL_PAYMENT                    0
TENURE                              0
dtype: int64

sb.heatmap(creditcard_df.isnull(), cmap='Oranges_r', yticklabels=False)

<AxesSubplot:>

Checking for any Duplicated Values

creditcard_df.duplicated().sum()

0

creditcard_df.drop('CUST_ID', axis = 1,inplace=True)

creditcard_df.columns

Index(['BALANCE', 'BALANCE_FREQUENCY', 'PURCHASES', 'ONEOFF_PURCHASES',
       'INSTALLMENTS_PURCHASES', 'CASH_ADVANCE', 'PURCHASES_FREQUENCY',
       'ONEOFF_PURCHASES_FREQUENCY', 'PURCHASES_INSTALLMENTS_FREQUENCY',
       'CASH_ADVANCE_FREQUENCY', 'CASH_ADVANCE_TRX', 'PURCHASES_TRX',
       'CREDIT_LIMIT', 'PAYMENTS', 'MINIMUM_PAYMENTS', 'PRC_FULL_PAYMENT',
       'TENURE'],
      dtype='object')

Exploratory Data Analysis

Hist and KDE(Kernal Density Estimate ) plots

plt.figure(figsize=(10,50))
for i in range(len(creditcard_df.columns)):
    plt.subplot(17, 1, i+1)
    sb.distplot(creditcard_df[creditcard_df.columns[i]],kde_kws={"color": "g", "lw": 2, "label": "KDE"}, hist_kws={"color": "r"})
    plt.title(creditcard_df.columns[i], color = 'b',size = 10)

plt.tight_layout()
plt.show()

C:\Users\Laxman Prasad\anaconda3\lib\site-packages\seaborn\distributions.py:2557: FutureWarning: `distplot` is a deprecated function and will be removed in a future version. Please adapt your code to use either `displot` (a figure-level function with similar flexibility) or `histplot` (an axes-level function for histograms).
  warnings.warn(msg, FutureWarning)
C:\Users\Laxman Prasad\anaconda3\lib\site-packages\seaborn\distributions.py:2557: FutureWarning: `distplot` is a deprecated function and will be removed in a future version. Please adapt your code to use either `displot` (a figure-level function with similar flexibility) or `histplot` (an axes-level function for histograms).
  warnings.warn(msg, FutureWarning)
C:\Users\Laxman Prasad\anaconda3\lib\site-packages\seaborn\distributions.py:2557: FutureWarning: `distplot` is a deprecated function and will be removed in a future version. Please adapt your code to use either `displot` (a figure-level function with similar flexibility) or `histplot` (an axes-level function for histograms).
  warnings.warn(msg, FutureWarning)
C:\Users\Laxman Prasad\anaconda3\lib\site-packages\seaborn\distributions.py:2557: FutureWarning: `distplot` is a deprecated function and will be removed in a future version. Please adapt your code to use either `displot` (a figure-level function with similar flexibility) or `histplot` (an axes-level function for histograms).
  warnings.warn(msg, FutureWarning)
C:\Users\Laxman Prasad\anaconda3\lib\site-packages\seaborn\distributions.py:2557: FutureWarning: `distplot` is a deprecated function and will be removed in a future version. Please adapt your code to use either `displot` (a figure-level function with similar flexibility) or `histplot` (an axes-level function for histograms).
  warnings.warn(msg, FutureWarning)
C:\Users\Laxman Prasad\anaconda3\lib\site-packages\seaborn\distributions.py:2557: FutureWarning: `distplot` is a deprecated function and will be removed in a future version. Please adapt your code to use either `displot` (a figure-level function with similar flexibility) or `histplot` (an axes-level function for histograms).
  warnings.warn(msg, FutureWarning)
C:\Users\Laxman Prasad\anaconda3\lib\site-packages\seaborn\distributions.py:2557: FutureWarning: `distplot` is a deprecated function and will be removed in a future version. Please adapt your code to use either `displot` (a figure-level function with similar flexibility) or `histplot` (an axes-level function for histograms).
  warnings.warn(msg, FutureWarning)
C:\Users\Laxman Prasad\anaconda3\lib\site-packages\seaborn\distributions.py:2557: FutureWarning: `distplot` is a deprecated function and will be removed in a future version. Please adapt your code to use either `displot` (a figure-level function with similar flexibility) or `histplot` (an axes-level function for histograms).
  warnings.warn(msg, FutureWarning)
C:\Users\Laxman Prasad\anaconda3\lib\site-packages\seaborn\distributions.py:2557: FutureWarning: `distplot` is a deprecated function and will be removed in a future version. Please adapt your code to use either `displot` (a figure-level function with similar flexibility) or `histplot` (an axes-level function for histograms).
  warnings.warn(msg, FutureWarning)
C:\Users\Laxman Prasad\anaconda3\lib\site-packages\seaborn\distributions.py:2557: FutureWarning: `distplot` is a deprecated function and will be removed in a future version. Please adapt your code to use either `displot` (a figure-level function with similar flexibility) or `histplot` (an axes-level function for histograms).
  warnings.warn(msg, FutureWarning)
C:\Users\Laxman Prasad\anaconda3\lib\site-packages\seaborn\distributions.py:2557: FutureWarning: `distplot` is a deprecated function and will be removed in a future version. Please adapt your code to use either `displot` (a figure-level function with similar flexibility) or `histplot` (an axes-level function for histograms).
  warnings.warn(msg, FutureWarning)
C:\Users\Laxman Prasad\anaconda3\lib\site-packages\seaborn\distributions.py:2557: FutureWarning: `distplot` is a deprecated function and will be removed in a future version. Please adapt your code to use either `displot` (a figure-level function with similar flexibility) or `histplot` (an axes-level function for histograms).
  warnings.warn(msg, FutureWarning)
C:\Users\Laxman Prasad\anaconda3\lib\site-packages\seaborn\distributions.py:2557: FutureWarning: `distplot` is a deprecated function and will be removed in a future version. Please adapt your code to use either `displot` (a figure-level function with similar flexibility) or `histplot` (an axes-level function for histograms).
  warnings.warn(msg, FutureWarning)
C:\Users\Laxman Prasad\anaconda3\lib\site-packages\seaborn\distributions.py:2557: FutureWarning: `distplot` is a deprecated function and will be removed in a future version. Please adapt your code to use either `displot` (a figure-level function with similar flexibility) or `histplot` (an axes-level function for histograms).
  warnings.warn(msg, FutureWarning)
C:\Users\Laxman Prasad\anaconda3\lib\site-packages\seaborn\distributions.py:2557: FutureWarning: `distplot` is a deprecated function and will be removed in a future version. Please adapt your code to use either `displot` (a figure-level function with similar flexibility) or `histplot` (an axes-level function for histograms).
  warnings.warn(msg, FutureWarning)
C:\Users\Laxman Prasad\anaconda3\lib\site-packages\seaborn\distributions.py:2557: FutureWarning: `distplot` is a deprecated function and will be removed in a future version. Please adapt your code to use either `displot` (a figure-level function with similar flexibility) or `histplot` (an axes-level function for histograms).
  warnings.warn(msg, FutureWarning)
C:\Users\Laxman Prasad\anaconda3\lib\site-packages\seaborn\distributions.py:2557: FutureWarning: `distplot` is a deprecated function and will be removed in a future version. Please adapt your code to use either `displot` (a figure-level function with similar flexibility) or `histplot` (an axes-level function for histograms).
  warnings.warn(msg, FutureWarning)

sb.pairplot(creditcard_df)
# Correlation between 'PURCHASES' and ONEOFF_PURCHASES & INSTALMENT_PURCHASES 
# Trend between 'PURCHASES' and 'CREDIT_LIMIT' & 'PAYMENTS'

<seaborn.axisgrid.PairGrid at 0x2b2be39e160>

Correlation

corr = creditcard_df.corr()

corr

	BALANCE	BALANCE_FREQUENCY	PURCHASES	ONEOFF_PURCHASES	INSTALLMENTS_PURCHASES	CASH_ADVANCE	PURCHASES_FREQUENCY	ONEOFF_PURCHASES_FREQUENCY	PURCHASES_INSTALLMENTS_FREQUENCY	CASH_ADVANCE_FREQUENCY	CASH_ADVANCE_TRX	PURCHASES_TRX	CREDIT_LIMIT	PAYMENTS	MINIMUM_PAYMENTS	PRC_FULL_PAYMENT	TENURE
BALANCE	1.000000	0.322412	0.181261	0.164350	0.126469	0.496692	-0.077944	0.073166	-0.063186	0.449218	0.385152	0.154338	0.531320	0.322802	0.394282	-0.318959	0.072692
BALANCE_FREQUENCY	0.322412	1.000000	0.133674	0.104323	0.124292	0.099388	0.229715	0.202415	0.176079	0.191873	0.141555	0.189626	0.096124	0.065008	0.114249	-0.095082	0.119776
PURCHASES	0.181261	0.133674	1.000000	0.916845	0.679896	-0.051474	0.393017	0.498430	0.315567	-0.120143	-0.067175	0.689561	0.356991	0.603264	0.093515	0.180379	0.086288
ONEOFF_PURCHASES	0.164350	0.104323	0.916845	1.000000	0.330622	-0.031326	0.264937	0.524891	0.127729	-0.082628	-0.046212	0.545523	0.319743	0.567292	0.048597	0.132763	0.064150
INSTALLMENTS_PURCHASES	0.126469	0.124292	0.679896	0.330622	1.000000	-0.064244	0.442418	0.214042	0.511351	-0.132318	-0.073999	0.628108	0.256533	0.384084	0.131687	0.182569	0.086143
CASH_ADVANCE	0.496692	0.099388	-0.051474	-0.031326	-0.064244	1.000000	-0.215507	-0.086754	-0.177070	0.628522	0.656498	-0.075850	0.304008	0.453238	0.139223	-0.152935	-0.068312
PURCHASES_FREQUENCY	-0.077944	0.229715	0.393017	0.264937	0.442418	-0.215507	1.000000	0.501343	0.862934	-0.308478	-0.203478	0.568430	0.119908	0.103464	0.002976	0.305802	0.061506
ONEOFF_PURCHASES_FREQUENCY	0.073166	0.202415	0.498430	0.524891	0.214042	-0.086754	0.501343	1.000000	0.142329	-0.111716	-0.069088	0.544869	0.295090	0.243537	-0.029963	0.157531	0.082466
PURCHASES_INSTALLMENTS_FREQUENCY	-0.063186	0.176079	0.315567	0.127729	0.511351	-0.177070	0.862934	0.142329	1.000000	-0.262958	-0.169207	0.529975	0.060851	0.085551	0.029590	0.250087	0.073275
CASH_ADVANCE_FREQUENCY	0.449218	0.191873	-0.120143	-0.082628	-0.132318	0.628522	-0.308478	-0.111716	-0.262958	1.000000	0.799561	-0.131168	0.132591	0.183192	0.097898	-0.249773	-0.133372
CASH_ADVANCE_TRX	0.385152	0.141555	-0.067175	-0.046212	-0.073999	0.656498	-0.203478	-0.069088	-0.169207	0.799561	1.000000	-0.066157	0.149728	0.255278	0.109185	-0.169784	-0.043421
PURCHASES_TRX	0.154338	0.189626	0.689561	0.545523	0.628108	-0.075850	0.568430	0.544869	0.529975	-0.131168	-0.066157	1.000000	0.272928	0.370832	0.095858	0.162066	0.121874
CREDIT_LIMIT	0.531320	0.096124	0.356991	0.319743	0.256533	0.304008	0.119908	0.295090	0.060851	0.132591	0.149728	0.272928	1.000000	0.421895	0.125167	0.055727	0.139486
PAYMENTS	0.322802	0.065008	0.603264	0.567292	0.384084	0.453238	0.103464	0.243537	0.085551	0.183192	0.255278	0.370832	0.421895	1.000000	0.125046	0.112138	0.106136
MINIMUM_PAYMENTS	0.394282	0.114249	0.093515	0.048597	0.131687	0.139223	0.002976	-0.029963	0.029590	0.097898	0.109185	0.095858	0.125167	0.125046	1.000000	-0.139674	0.057257
PRC_FULL_PAYMENT	-0.318959	-0.095082	0.180379	0.132763	0.182569	-0.152935	0.305802	0.157531	0.250087	-0.249773	-0.169784	0.162066	0.055727	0.112138	-0.139674	1.000000	-0.016486
TENURE	0.072692	0.119776	0.086288	0.064150	0.086143	-0.068312	0.061506	0.082466	0.073275	-0.133372	-0.043421	0.121874	0.139486	0.106136	0.057257	-0.016486	1.000000

plt.figure(figsize=(15,15))
sb.heatmap(creditcard_df.corr(), yticklabels=True, cmap = 'Accent_r', annot=True)

<AxesSubplot:>

Feature Scalling

from sklearn.preprocessing import StandardScaler
scaler = StandardScaler()
creditcard_df_scaled= scaler.fit_transform(creditcard_df)

creditcard_df_scaled

array([[-0.73198937, -0.24943448, -0.42489974, ..., -0.31096755,
        -0.52555097,  0.36067954],
       [ 0.78696085,  0.13432467, -0.46955188, ...,  0.08931021,
         0.2342269 ,  0.36067954],
       [ 0.44713513,  0.51808382, -0.10766823, ..., -0.10166318,
        -0.52555097,  0.36067954],
       ...,
       [-0.7403981 , -0.18547673, -0.40196519, ..., -0.33546549,
         0.32919999, -4.12276757],
       [-0.74517423, -0.18547673, -0.46955188, ..., -0.34690648,
         0.32919999, -4.12276757],
       [-0.57257511, -0.88903307,  0.04214581, ..., -0.33294642,
        -0.52555097, -4.12276757]])

creditcard_df_scaled.shape

(8950, 17)

Finding Optimal Number of Clusters1

from sklearn.cluster import KMeans
wcss = []
for i in range(1,20):
    Kmeans = KMeans(n_clusters=i)
    Kmeans.fit(creditcard_df_scaled)
    wcss.append(Kmeans.inertia_)
plt.plot(wcss, 'r*-', markersize=10)
plt.title('Plot to find number of clusters', color = 'Red', size = 15)
plt.xlabel('Clusters', color = 'Blue', size = 12)
plt.ylabel('wcss scores', color = 'Blue', size = 12) 
plt.show()

Identified cluster number is appling on each column for the scaled data

Kmeans = KMeans(8,init='k-means++') 
#intit is to avoid taking the model centre point as centroid
Kmeans.fit(creditcard_df_scaled)

KMeans()

Finding the labels

labels = Kmeans.labels_

labels.shape

(8950,)

labels.min()

0

labels.max()

7

Kmeans.labels_

array([1, 6, 5, ..., 2, 2, 2])

Kmeans.labels_.dtype

dtype('int32')

Kmeans.labels_

array([1, 6, 5, ..., 2, 2, 2])

To display the centroids1

Kmeans.cluster_centers_

array([[-3.36049587e-01, -3.47077860e-01, -2.89266864e-01,
        -2.15966042e-01, -2.86835279e-01,  6.82835664e-02,
        -2.03077759e-01, -2.88661118e-01, -2.24548914e-01,
         3.08663197e-01,  9.96472666e-04, -3.88116768e-01,
        -5.68620439e-01, -3.92679966e-01, -2.09145007e-01,
         1.40113780e-02, -3.20373299e+00],
       [-7.01229283e-01, -2.14411628e+00, -3.11098786e-01,
        -2.35720118e-01, -3.02413627e-01, -3.21904751e-01,
        -5.56586290e-01, -4.44988775e-01, -4.39729749e-01,
        -5.20843751e-01, -3.76102518e-01, -4.19789965e-01,
        -1.77040035e-01, -2.02048177e-01, -2.56658204e-01,
         2.81550499e-01,  1.99199458e-01],
       [ 1.88267000e-02,  4.03379486e-01, -3.62129153e-01,
        -2.47327073e-01, -4.01753170e-01, -8.93531552e-02,
        -8.67254702e-01, -4.10337326e-01, -7.58633418e-01,
         1.12552518e-01, -2.25036977e-02, -4.87082010e-01,
        -3.05667743e-01, -2.49499439e-01, -3.67394168e-03,
        -4.57045384e-01,  2.72461662e-01],
       [-3.66739830e-01,  3.33338380e-01, -3.85389595e-02,
        -2.44302992e-01,  3.57516154e-01, -3.63618503e-01,
         9.90253126e-01, -3.87060270e-01,  1.20549554e+00,
        -4.75146398e-01, -3.61199635e-01,  1.86768973e-01,
        -2.61189644e-01, -2.17939671e-01, -4.59793867e-02,
         3.14958533e-01,  2.57483792e-01],
       [ 1.69145526e+00,  3.92898471e-01, -2.17992157e-01,
        -1.56311793e-01, -2.28334747e-01,  2.02894159e+00,
        -4.77769879e-01, -2.12558400e-01, -4.14961382e-01,
         1.92718079e+00,  1.94262279e+00, -2.66771670e-01,
         1.03161365e+00,  8.26932696e-01,  5.13220493e-01,
        -3.90436041e-01,  7.02783875e-02],
       [ 9.19935407e-01,  4.67655287e-01,  2.25449078e+00,
         1.72111588e+00,  2.16875635e+00, -1.93345936e-01,
         1.16056707e+00,  1.55482581e+00,  1.24634100e+00,
        -3.09466958e-01, -2.09799089e-01,  2.78190077e+00,
         1.22528374e+00,  1.28391524e+00,  5.66182497e-01,
         2.88329286e-01,  3.34055749e-01],
       [ 1.92305052e+00,  3.37716867e-01,  1.12120418e+01,
         1.06003671e+01,  7.03311838e+00,  4.19625127e-01,
         1.04698328e+00,  1.91550149e+00,  9.81333653e-01,
        -2.58911831e-01,  6.12285458e-02,  5.36243850e+00,
         3.04400629e+00,  8.09897492e+00,  1.12031761e+00,
         1.11013157e+00,  3.10863465e-01],
       [-1.62727000e-01,  3.92065093e-01,  4.63858580e-01,
         6.06423226e-01, -1.74695827e-02, -3.33497066e-01,
         9.42521833e-01,  1.87730926e+00,  8.89931125e-02,
        -4.08096446e-01, -3.23289849e-01,  5.28626139e-01,
         3.83552937e-01,  9.37912723e-02, -1.62173705e-01,
         4.07629642e-01,  2.61092550e-01]])

Kmeans.cluster_centers_.shape

(8, 17)

Kmeans.cluster_centers_.size

136

Centroids represented in the dataframe

cluster_centers = pd.DataFrame(data = Kmeans.cluster_centers_, columns = [creditcard_df.columns])
cluster_centers

	BALANCE	BALANCE_FREQUENCY	PURCHASES	ONEOFF_PURCHASES	INSTALLMENTS_PURCHASES	CASH_ADVANCE	PURCHASES_FREQUENCY	ONEOFF_PURCHASES_FREQUENCY	PURCHASES_INSTALLMENTS_FREQUENCY	CASH_ADVANCE_FREQUENCY	CASH_ADVANCE_TRX	PURCHASES_TRX	CREDIT_LIMIT	PAYMENTS	MINIMUM_PAYMENTS	PRC_FULL_PAYMENT	TENURE
0	-0.336050	-0.347078	-0.289267	-0.215966	-0.286835	0.068284	-0.203078	-0.288661	-0.224549	0.308663	0.000996	-0.388117	-0.568620	-0.392680	-0.209145	0.014011	-3.203733
1	-0.701229	-2.144116	-0.311099	-0.235720	-0.302414	-0.321905	-0.556586	-0.444989	-0.439730	-0.520844	-0.376103	-0.419790	-0.177040	-0.202048	-0.256658	0.281550	0.199199
2	0.018827	0.403379	-0.362129	-0.247327	-0.401753	-0.089353	-0.867255	-0.410337	-0.758633	0.112553	-0.022504	-0.487082	-0.305668	-0.249499	-0.003674	-0.457045	0.272462
3	-0.366740	0.333338	-0.038539	-0.244303	0.357516	-0.363619	0.990253	-0.387060	1.205496	-0.475146	-0.361200	0.186769	-0.261190	-0.217940	-0.045979	0.314959	0.257484
4	1.691455	0.392898	-0.217992	-0.156312	-0.228335	2.028942	-0.477770	-0.212558	-0.414961	1.927181	1.942623	-0.266772	1.031614	0.826933	0.513220	-0.390436	0.070278
5	0.919935	0.467655	2.254491	1.721116	2.168756	-0.193346	1.160567	1.554826	1.246341	-0.309467	-0.209799	2.781901	1.225284	1.283915	0.566182	0.288329	0.334056
6	1.923051	0.337717	11.212042	10.600367	7.033118	0.419625	1.046983	1.915501	0.981334	-0.258912	0.061229	5.362438	3.044006	8.098975	1.120318	1.110132	0.310863
7	-0.162727	0.392065	0.463859	0.606423	-0.017470	-0.333497	0.942522	1.877309	0.088993	-0.408096	-0.323290	0.528626	0.383553	0.093791	-0.162174	0.407630	0.261093

Performing Inverese Transform to get datapoints in orginal form

cluster_centers = scaler.inverse_transform(cluster_centers)
cluster_centers = pd.DataFrame(data = cluster_centers, columns = [creditcard_df.columns])
cluster_centers

	BALANCE	BALANCE_FREQUENCY	PURCHASES	ONEOFF_PURCHASES	INSTALLMENTS_PURCHASES	CASH_ADVANCE	PURCHASES_FREQUENCY	ONEOFF_PURCHASES_FREQUENCY	PURCHASES_INSTALLMENTS_FREQUENCY	CASH_ADVANCE_FREQUENCY	CASH_ADVANCE_TRX	PURCHASES_TRX	CREDIT_LIMIT	PAYMENTS	MINIMUM_PAYMENTS	PRC_FULL_PAYMENT	TENURE
0	865.015978	0.795051	385.181720	233.977974	151.686061	1122.064941	0.408846	0.116344	0.275196	0.196911	3.255627	5.062701	2425.054994	596.373827	376.802926	0.157813	7.229904
1	104.925267	0.369349	338.537483	201.190254	137.598754	303.821813	0.266966	0.069709	0.189677	0.030918	0.682203	4.275424	3849.863936	1148.234177	266.075424	0.236063	11.783898
2	1603.661014	0.972828	229.510316	181.925086	47.767238	791.493372	0.142279	0.080046	0.062937	0.157667	3.095256	2.602795	3381.837685	1010.867422	855.644576	0.020037	11.881942
3	801.136827	0.956236	920.865753	186.944441	734.365067	216.346127	0.887787	0.086990	0.843532	0.040063	0.783905	19.352211	3543.676206	1102.229857	757.053521	0.245835	11.861898
4	5085.096182	0.970345	537.461230	332.991810	204.587367	5233.656408	0.298598	0.139047	0.199521	0.520793	16.505800	8.078886	8247.685088	4127.032982	2060.245252	0.039519	11.611369
5	3479.242725	0.988054	5819.959145	3449.137221	2372.247102	573.415653	0.956142	0.666292	0.859765	0.073217	1.817102	83.857482	8952.375297	5449.952679	2183.670969	0.238046	11.964371
6	5567.142164	0.957273	24957.905000	18186.875667	6771.029333	1858.844605	0.910556	0.773889	0.754444	0.083333	3.666667	148.000000	15570.000000	25178.882690	3475.059479	0.478409	11.933333
7	1225.772313	0.970147	1994.245839	1598.975721	395.270118	279.512186	0.868630	0.762495	0.399805	0.053480	1.042611	27.849501	5889.643946	2004.660395	486.267564	0.272939	11.866727

#865.015978 is the one centroid

y_pred_Kmeans = Kmeans.fit_predict(creditcard_df_scaled)
y_pred_Kmeans

array([1, 3, 4, ..., 5, 5, 5])

y_pred_Kmeans.shape

(8950,)

concatenate the clusters labels to our original dataframe

creditcard_df_cluster = pd.concat([creditcard_df, pd.DataFrame({'cluster':labels})], axis = 1)
creditcard_df_cluster.head()

	BALANCE	BALANCE_FREQUENCY	PURCHASES	ONEOFF_PURCHASES	INSTALLMENTS_PURCHASES	CASH_ADVANCE	PURCHASES_FREQUENCY	ONEOFF_PURCHASES_FREQUENCY	PURCHASES_INSTALLMENTS_FREQUENCY	CASH_ADVANCE_FREQUENCY	CASH_ADVANCE_TRX	PURCHASES_TRX	CREDIT_LIMIT	PAYMENTS	MINIMUM_PAYMENTS	PRC_FULL_PAYMENT	TENURE	cluster
0	40.900749	0.818182	95.40	0.00	95.4	0.000000	0.166667	0.000000	0.083333	0.000000	0	2	1000.0	201.802084	139.509787	0.000000	12	2
1	3202.467416	0.909091	0.00	0.00	0.0	6442.945483	0.000000	0.000000	0.000000	0.250000	4	0	7000.0	4103.032597	1072.340217	0.222222	12	4
2	2495.148862	1.000000	773.17	773.17	0.0	0.000000	1.000000	1.000000	0.000000	0.000000	0	12	7500.0	622.066742	627.284787	0.000000	12	7
3	1666.670542	0.636364	1499.00	1499.00	0.0	205.788017	0.083333	0.083333	0.000000	0.083333	1	1	7500.0	0.000000	864.206542	0.000000	12	2
4	817.714335	1.000000	16.00	16.00	0.0	0.000000	0.083333	0.083333	0.000000	0.000000	0	1	1200.0	678.334763	244.791237	0.000000	12	2

Dimensional Reduction

Principle Component Analysis

from sklearn.decomposition import PCA
pca = PCA(n_components= 3)
principal_comp = pca.fit_transform(creditcard_df_scaled)
principal_comp

array([[-1.68225769, -1.07630908,  0.48864524],
       [-1.13810768,  2.50656929,  0.60157448],
       [ 0.96974331, -0.38351454,  0.10217595],
       ...,
       [-0.92638881, -1.81085314, -0.4749828 ],
       [-2.33669015, -0.65798024,  0.9745684 ],
       [-0.55658195, -0.40062203,  1.0153537 ]])

principal_comp.shape

(8950, 3)

pca_df = pd.DataFrame(data = principal_comp, columns =['pca1','pca2', 'pca3'])
pca_df.head()

	pca1	pca2	pca3
0	-1.682258	-1.076309	0.488645
1	-1.138108	2.506569	0.601574
2	0.969743	-0.383515	0.102176
3	-0.873565	0.043210	1.460065
4	-1.599441	-0.688422	0.365168

pca_df.dtypes

pca1    float64
pca2    float64
pca3    float64
dtype: object

pca_df.value_counts()

pca1        pca2       pca3        cluster
-2.765679   -0.874989   2.076017   0          1
 0.302727   -0.779982  -1.629229   3          1
 0.299038   -1.352426  -1.665409   3          1
 0.299403   -1.665631  -1.712216   3          1
 0.299650    0.642995  -0.774394   2          1
                                             ..
-1.190486   -1.060328   1.356908   1          1
-1.190502   -0.566636   0.678175   2          1
-1.190849   -0.770999   0.756511   0          1
-1.190974   -0.569213   0.165596   2          1
 29.605347   3.538914   10.076441  6          1
Length: 8950, dtype: int64

# Concatenate the clusters labels to the dataframe
pca_df = pd.concat([pca_df,pd.DataFrame({'cluster':labels})], axis = 1)
pca_df.head()

	pca1	pca2	pca3	cluster
0	-1.682258	-1.076309	0.488645	2
1	-1.138108	2.506569	0.601574	4
2	0.969743	-0.383515	0.102176	7
3	-0.873565	0.043210	1.460065	2
4	-1.599441	-0.688422	0.365168	2

plt.figure(figsize=(10,10))
df = sb.scatterplot(x="pca1", y="pca2", hue = "cluster", data = pca_df)
plt.show()

plt.figure(figsize=(10,10))
df = sb.scatterplot(x="pca1", y="pca2", hue = "cluster", data = pca_df,  palette =['red','green','blue','pink','yellow','gray','purple', 'black'])
plt.show()

plt.figure(figsize=(10,10))
df = sb.scatterplot(x="pca2",hue = "cluster", data = pca_df)
plt.show()